Computer Rating System Prediction Results for College Football (NCAA IA)

2013 Season Totals

Through 2014-01-07
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Ted Thompson SPRS0.780950.5180112.2721-0.3005237.926735574161374348
2Pi-Rate Ratings0.778230.5278612.4221-0.2736240.139735572163379339
3Ed Bemiss0.777290.5140712.4644-0.5365244.947687534153347328
4Line (midweek)0.7768712.29930.0564237.080735571164
5Ashby AccuRatings0.775510.5126712.4695-0.7169247.691735570165344327
6Catherwood Ratings0.775200.5563712.50000.1717247.721734569165380303
7Ted Thompson Avg0.774150.5208912.3430-0.0288238.419735569166374344
8Dave Congrove0.772790.5574012.8916-1.2192263.202735568167403320
9Keeper0.771430.5256612.94920.5517262.321735567168379342
10PI-Rate Bias0.771430.5208312.5039-0.2827242.613735567168375345
11System Median0.771430.5132512.3099-0.2693239.833735567168368349
12Computer Adjusted Line0.770070.5503712.23610.0621235.295735566169295241
13Line (updated)0.770070.5426212.25030.1086235.782735566169261220
14Atomic Football0.768710.5262412.54050.0574247.132735565170381343
15Born Power Index0.768710.5442012.6603-0.3303254.418735565170394330
16Sagarin0.767350.5013812.65800.5580255.164735564171363361
17CPA Rankings0.767350.5690612.57010.2011252.810735564171412312
18Line (opening)0.767350.5016112.3837-0.3629239.927735564171312310
19System Average0.767350.5193912.3253-0.2443240.200735564171375347
20DP Dwiggins0.766390.5208612.9235-0.6184260.142732561171362333
21Sagarin Curve0.765990.5110512.70570.5502258.828735563172370354
22Sagarin Predictor0.765990.5034612.70240.5510256.642735563172364359
23Moore Power Ratings0.765670.5367512.6350-0.3135252.930734562172387334
24Dokter Entropy0.764630.5311212.33830.2897243.134735562173384339
25Compughter Ratings0.763490.5449412.7334-1.1624260.142723552171388324
26Pigskin Index0.763270.5198812.3375-0.5496239.961735561174353326
27Stat Fox0.763270.5247812.66410.6760252.813735561174360326
28Directorofinformation0.763270.4834312.8039-0.0680257.547735561174350374
29Massey Consensus0.761900.4944812.9335-0.4676262.700735560175358366
30Pi-Ratings Mean0.760540.4923312.9267-0.5317257.579735559176353364
31Edward Kambour0.759280.5062913.0465-0.2069267.895727552175362353
32Lee Burdorf0.758530.5256612.7262-0.3715260.079733556177379342
33Daniel Curry Index0.756640.5221112.9270-0.2385267.147715541174366335
34Payne Power Ratings0.756460.5331513.0407-0.5542265.786735556179386338
35Billingsley+0.755100.4951612.8360-0.2635258.461735555180358365
36Laz Index0.755100.5117612.8035-1.0857257.243735555180370353
37Massey Ratings0.755100.5075512.6981-0.2256256.067735555180336326
38ARGH Power Ratings0.755100.5181412.66460.0432256.311735555180357332
39The Power Rank0.752410.4915513.0835-0.7232272.642727547180349361
40Regression-Based Analys0.751710.4919913.59350.5229287.790733551182338349
41Fremeau FEI0.750680.5035713.5668-2.4821288.452734551183353348
42Tempo Free Gridiron0.750340.4751114.3397-3.0043323.431733550183334369
43Brent Craig0.747610.5387812.8853-0.7100263.068733548185389333
44Donchess Inference0.746250.5302613.4775-1.1748293.049733547186368326
45Stephen Kerns0.745580.4902513.0529-1.0835267.360735548187352366
46Dunkel Index0.744220.4986213.2086-0.8031277.096735547188361363
47Beck Elo0.744220.4951613.1360-0.7215265.776735547188358365
48Howell0.742510.4985413.09940.2023276.202734545189341343
49PerformanZ Ratings0.738780.5207213.3551-0.8363282.219735543192377347
50CPA Retro0.736050.5359113.21860.0851285.751735541194388336
51Linear Regression0.735540.5593212.90390.0351258.55236326796198156
52Wolfe *0.732780.5084713.33970.7526285.83636326697180174
53Bihl System0.728160.5086812.94520.7886254.846412300112205198
54Laffaye RWP0.727520.5242014.1570-2.2195311.442734534200379344
55Marsee0.727520.5256413.54501.1888291.153734534200369333
56NutShell Sports0.726530.4971514.0611-1.2702309.710735534201349353
57PointShare Ratings0.726070.5226913.8289-1.0954297.686606440166311284
58Billingsley0.725170.4875714.0713-1.0123310.275735533202353371
59Super List0.721090.4923914.4654-0.6876326.516735530205356367
60Covers.com0.719730.4701814.4970-1.5563325.507735529206339382
61Martien Maas0.719510.4987513.5263-0.1419285.530410295115199200
62Anderson/Hester *0.716250.5056513.30760.0475279.275363260103179175
63Laffaye XWP0.714700.4904015.36055.5202379.123687491196332345
64Colley Rankings *0.713500.4915313.39350.0266283.029363259104174180
65Sportrends0.711960.4799414.2718-1.2874319.845677482195311337
66Massey *0.705230.5169513.71480.8972306.395363256107183171
67football.loudsound.org0.700270.5021814.6798-5.0157339.031734514220345342
68Least Squares w/ HFA0.696970.4900815.46640.4178363.790363253110173180
69Sagrin Pure Elo0.695120.5100013.95802.1303312.075410285125204196
70Logistic Regression0.663910.5014215.03810.2812355.700363241122177176

* This system does not make predictions.  I make predictions for this
  system by translating it to a new scale that allows for making predictions.



Retrodictive records are found by taking the ratings from the current week
and applying them to the entire season to date.

The ideal system would be one that has the highest correct game decisions,
has the smallest mean error(deviation from the actual game result), and has
a bias of zero.

Mean Error = average[abs(prediction-actual)]

      Bias = agerage(prediction - actual)

      Std. = Standard Deviation of individual game biases